Melanoma vs Seborreic_Keratosis
Loading data sets
op <- par(no.readonly = TRUE)
MelanomaFeatures <- read.csv("/Users/juanluis/Downloads/LearningMelanoma/MelanomaLesionFeatures.csv", header=FALSE)
SeborrheicFeatures <- read.csv("/Users/juanluis/Downloads/LearningMelanoma/SeborrheicLesionFeatures.csv", header=FALSE)
MelanomaControlFeatures <- read.csv("/Users/juanluis/Downloads/LearningMelanoma/MelanomaControlFeatures.csv", header=FALSE)
SeborrheicControlFeatures <- read.csv("/Users/juanluis/Downloads/LearningMelanoma/SeborrheicControlFeatures.csv", header=FALSE)
LesionFeatureNames <- read_excel("/Users/juanluis/Downloads/LearningMelanoma/FeatureNames.xlsx")
ControlFeatureNames <- read_excel("/Users/juanluis/Downloads/LearningMelanoma/FeatureNames.xlsx",sheet = "Control")
FeatureNames <- read_excel("/Users/juanluis/Downloads/LearningMelanoma/FeatureNames.xlsx",sheet = "PerChannel")
colnames(MelanomaFeatures) <- LesionFeatureNames$FinalName
colnames(SeborrheicFeatures) <- LesionFeatureNames$FinalName
colnames(MelanomaControlFeatures) <- ControlFeatureNames$FinalName
colnames(SeborrheicControlFeatures) <- ControlFeatureNames$FinalName
sum(is.na(MelanomaFeatures))
sum(is.na(SeborrheicFeatures))
sum(is.na(MelanomaControlFeatures))
channel1 <- c(1:32)
channel2 <- c(33:64)
channel3 <- c(65:96)
MMelanomaFeatures <- ( MelanomaFeatures[,channel1] +
MelanomaFeatures[,channel2] +
MelanomaFeatures[,channel3] )/3.0
SMelanomaFeatures <- ( abs(MelanomaFeatures[,channel1] - MMelanomaFeatures) +
abs(MelanomaFeatures[,channel2] - MMelanomaFeatures) +
abs(MelanomaFeatures[,channel3] - MMelanomaFeatures) )/3.0
colnames(MMelanomaFeatures) <- paste("M",FeatureNames$Features,sep="")
colnames(SMelanomaFeatures) <- paste("S",FeatureNames$Features,sep="")
MelanomaFeatures <- cbind(MelanomaFeatures,SMelanomaFeatures/(0.01+abs(MMelanomaFeatures)))
MSeborrheicFeatures <- ( SeborrheicFeatures[,channel1] +
SeborrheicFeatures[,channel2] +
SeborrheicFeatures[,channel3] )/3.0
SSeborrheicFeatures <- (abs(SeborrheicFeatures[,channel1] - MSeborrheicFeatures) +
abs(SeborrheicFeatures[,channel2] - MSeborrheicFeatures) +
abs(SeborrheicFeatures[,channel3] - MSeborrheicFeatures))/3.0
colnames(MSeborrheicFeatures) <- paste("M",FeatureNames$Features,sep="")
colnames(SSeborrheicFeatures) <- paste("S",FeatureNames$Features,sep="")
SeborrheicFeatures <- cbind(SeborrheicFeatures,SSeborrheicFeatures/(0.001+abs(MSeborrheicFeatures)))
MMelanomaControlFeatures <- ( MelanomaControlFeatures[,channel1] +
MelanomaControlFeatures[,channel2] +
MelanomaControlFeatures[,channel3] )/3.0
SMelanomaControlFeatures <- (abs(MelanomaControlFeatures[,channel1] - MMelanomaControlFeatures) +
abs(MelanomaControlFeatures[,channel2] - MMelanomaControlFeatures) +
abs(MelanomaControlFeatures[,channel3] - MMelanomaControlFeatures))/3.0
colnames(MMelanomaControlFeatures) <- paste("M_C",FeatureNames$Features,sep="")
colnames(SMelanomaControlFeatures) <- paste("S_C",FeatureNames$Features,sep="")
MelanomaControlFeatures <- cbind(MelanomaControlFeatures,SMelanomaControlFeatures/(0.001+abs(MMelanomaControlFeatures)))
MSeborrheicControlFeatures <- ( SeborrheicControlFeatures[,channel1] +
SeborrheicControlFeatures[,channel2] +
SeborrheicControlFeatures[,channel3] )/3.0
SSeborrheicControlFeatures <- (abs(SeborrheicControlFeatures[,channel1] - MSeborrheicControlFeatures) +
abs(SeborrheicControlFeatures[,channel2] - MSeborrheicControlFeatures) +
abs(SeborrheicControlFeatures[,channel3] - MSeborrheicControlFeatures))/3.0
colnames(MSeborrheicControlFeatures) <- paste("M_C",FeatureNames$Features,sep="")
colnames(SSeborrheicControlFeatures) <- paste("S_C",FeatureNames$Features,sep="")
SeborrheicControlFeatures <- cbind(SeborrheicControlFeatures,
SSeborrheicControlFeatures/(0.001+abs(MSeborrheicControlFeatures)))
CtrDiff <- MelanomaFeatures[,1:ncol(MelanomaControlFeatures)] - MelanomaControlFeatures;
colnames(CtrDiff) <- colnames(MelanomaControlFeatures)
MelanomaFeatures <- cbind(MelanomaFeatures,CtrDiff)
CtrDiff <- SeborrheicFeatures[,1:ncol(MelanomaControlFeatures)] - SeborrheicControlFeatures;
colnames(CtrDiff) <- colnames(SeborrheicControlFeatures)
SeborrheicFeatures <- cbind(SeborrheicFeatures,CtrDiff)
MelanomaFeatures <- MelanomaFeatures[complete.cases(MelanomaFeatures),]
SeborrheicFeatures <- SeborrheicFeatures[complete.cases(SeborrheicFeatures),]
MelanomaFeatures$Class <- rep(1,nrow(MelanomaFeatures))
SeborrheicFeatures$Class <- rep(0,nrow(SeborrheicFeatures))
MelanomaSeborrheic <- rbind(MelanomaFeatures,SeborrheicFeatures)
table(MelanomaSeborrheic$Class)
The Heatmap
par(op)
par(mar=c(10,5,5,5))
boxplot(MelanomaSeborrheic,las=2,cex=0.5,cex.axis=0.5,main="Features")
par(op)
hm <- heatMaps(Outcome = "Class",
data = MelanomaSeborrheic,
title = "Heat Map:",Scale = TRUE,
hCluster = "col",cexRow = 0.75,cexCol = 0.35,srtCol = 45)
uks <- univariate_KS(MelanomaSeborrheic,"Class")
par(mar=c(5,15,5,5))
barplot(-log(1.0e-12+uks[1:20]),las=2,xlab="Log(pvalue)",cex.names = 0.65,main="Top Features",horiz=TRUE)
print(uks[1:20])
#> C_Blue_Red_Mean C_Blue_Red_Compactness
#> 0.000000e+00 0.000000e+00
#> C_Blue_Red_GradientRatios C_Green_Compactness
#> 0.000000e+00 2.864375e-14
#> C_Green_Mean C_Red_Green_Mean
#> 9.166001e-14 1.145750e-13
#> C_Blue_Red_Skewness C_Blue_Red_Fractal_Homogeneity
#> 2.243215e-11 4.889171e-11
#> L_Green_Energy_2 C_Blue_Red_Gradient
#> 4.889171e-11 1.475812e-10
#> C_Red_Green_Fractal_Homogeneity L_Green_Mean
#> 4.390983e-10 4.829891e-10
#> L_Green_90COV SHomogeneity_8
#> 4.829891e-10 4.829891e-10
#> L_Blue_Red_Gradient S_CFractal_Correlation
#> 4.829891e-10 5.100486e-10
#> C_Green_COV C_Red_Green_GradientRatios
#> 1.396939e-09 3.274915e-09
#> SSkewness L_Green_Correlation_8
#> 3.351653e-09 5.488690e-09
par(op)
Learning Melanoma with KNN
cvKNN <- randomCV(MelanomaSeborrheic,"Class",
KNN_method,
trainFraction = 0.90,
repetitions = 100,
classSamplingType = "Pro",
featureSelectionFunction = univariate_KS,
featureSelection.control = list(pvalue=0.05,limit= -1),
kn=5
)
#> ..........10 Tested: 337 Avg. Selected: 162.2 Min Tests: 1 Max Tests: 4 Mean Tests: 1.5727 . MAD: 0.2955375
#>
..........20 Tested: 470 Avg. Selected: 161.9 Min Tests: 1 Max Tests: 6 Mean Tests: 2.255319 . MAD: 0.2835806
#>
..........30 Tested: 507 Avg. Selected: 160.7333 Min Tests: 1 Max Tests: 9 Mean Tests: 3.136095 . MAD: 0.2869673
#>
..........40 Tested: 519 Avg. Selected: 160.35 Min Tests: 1 Max Tests: 10 Mean Tests: 4.084778 . MAD: 0.2883238
#>
..........50 Tested: 521 Avg. Selected: 160.04 Min Tests: 1 Max Tests: 11 Mean Tests: 5.086372 . MAD: 0.2888887
#>
..........60 Tested: 522 Avg. Selected: 159.5667 Min Tests: 1 Max Tests: 14 Mean Tests: 6.091954 . MAD: 0.2886474
#>
..........70 Tested: 523 Avg. Selected: 159.4 Min Tests: 1 Max Tests: 14 Mean Tests: 7.09369 . MAD: 0.2899441
#>
..........80 Tested: 523 Avg. Selected: 159.4 Min Tests: 2 Max Tests: 15 Mean Tests: 8.107075 . MAD: 0.2897717
#>
..........90 Tested: 523 Avg. Selected: 159.1444 Min Tests: 3 Max Tests: 16 Mean Tests: 9.120459 . MAD: 0.2907818
#>
..........100 Tested: 523 Avg. Selected: 159.06 Min Tests: 3 Max Tests: 18 Mean Tests: 10.13384 . MAD: 0.2902349
#>
Learning Melanoma with KNN
cvKNN <- randomCV(MelanomaSeborrheic,"Class",
KNN_method,
trainFraction = 0.90,
repetitions = 100,
classSamplingType = "Pro",
featureSelectionFunction = univariate_KS,
featureSelection.control = list(pvalue=0.05,limit= -1),
kn=10
)
#> ..........10 Tested: 344 Avg. Selected: 157.2 Min Tests: 1 Max Tests: 4 Mean Tests: 1.540698 . MAD: 0.3211822
#>
..........20 Tested: 456 Avg. Selected: 157.9 Min Tests: 1 Max Tests: 7 Mean Tests: 2.324561 . MAD: 0.3078315
#>
..........30 Tested: 504 Avg. Selected: 157.6333 Min Tests: 1 Max Tests: 9 Mean Tests: 3.154762 . MAD: 0.3101084
#>
..........40 Tested: 515 Avg. Selected: 158.375 Min Tests: 1 Max Tests: 11 Mean Tests: 4.116505 . MAD: 0.3108356
#>
..........50 Tested: 520 Avg. Selected: 158.92 Min Tests: 1 Max Tests: 12 Mean Tests: 5.096154 . MAD: 0.3111129
#>
..........60 Tested: 523 Avg. Selected: 159 Min Tests: 1 Max Tests: 15 Mean Tests: 6.080306 . MAD: 0.3110844
#>
..........70 Tested: 523 Avg. Selected: 159.2571 Min Tests: 1 Max Tests: 16 Mean Tests: 7.09369 . MAD: 0.3103481
#>
..........80 Tested: 523 Avg. Selected: 159.325 Min Tests: 2 Max Tests: 18 Mean Tests: 8.107075 . MAD: 0.3101212
#>
..........90 Tested: 523 Avg. Selected: 159.1222 Min Tests: 3 Max Tests: 19 Mean Tests: 9.120459 . MAD: 0.3092068
#>
..........100 Tested: 523 Avg. Selected: 159.22 Min Tests: 3 Max Tests: 20 Mean Tests: 10.13384 . MAD: 0.3098905
#>
